We rendered and embedded one million CAD files
cad-search-three.vercel.app
We rendered and embedded one million CAD files
1–10 of 51 posts
Re: We rendered and embedded one million CAD files
#2We rendered the one million part ABC dataset from Deep Geometry, and open-sourced the data. We also built a fun demo with the following pipeline: CAD > render > caption > embed.
Open-sourced dataset: https://huggingface.co/datasets/daveferbear/3d-model-images-...
Blog writeup: https://www.finalrev.com/blog/embedding-one-million-3d-model...
Re: We rendered and embedded one million CAD files
#3Interesting.
My go-to for CAD files is usually https://grabcad.com/library
I searched this for "WAGO" and "XT90", so I guess not the same use case. Some hits for "Raspberry Pi", though.
Re: We rendered and embedded one million CAD files
#4Interesting. My go-to for CAD files is usually https://grabcad.com/library I searched this for "WAGO" and "XT90", so I guess not the same use case. Some hits for "Raspberry Pi", though.
This isn't meant to be a commercially useful search engine- just a demonstration. You'll only be able to search for terms that the VLM could directly discern.
From the blog post: Our search demo proves that it works quite well. As anticipated, text search works well, returning sensible results for even irregular or poorly formed queries. It’s worth mentioning that this is very different from 3D part libraries like Thingiverse or GrabCAD. Search in those repositories requires users to tag or annotate parts with a description, the text of which is used in search. Our system takes only an unnamed part as input, requiring no additional labelling.
Re: We rendered and embedded one million CAD files
#5Interesting. My go-to for CAD files is usually https://grabcad.com/library I searched this for "WAGO" and "XT90", so I guess not the same use case. Some hits for "Raspberry Pi", though.
This isn't meant to be a commercially useful search engine- just a demonstration. You'll only be able to search for terms that the VLM could directly discern. From the blog post: Our search demo proves that it works quite well. As anticipated, text search works well, returning sensible results for even irregular or poorly formed queries. It’s worth mentioning that this is very different from 3D part libraries like Th…
I see, you did an AI demo of captioning and search over captures specifically for complex geometric objects.
I guess my interest was more piqued by the "CAD" part.
Re: We rendered and embedded one million CAD files
#6i tried “apples” and got lots of nuts-and-bolts models?
edit: looks like the data is trained from machinery parts. impressive regardless, but i’d add that to the lander
Re: We rendered and embedded one million CAD files
#7i tried “apples” and got lots of nuts-and-bolts models? edit: looks like the data is trained from machinery parts. impressive regardless, but i’d add that to the lander
There's a pretty big bias for mechanical engineering components in the dataset- very few organic forms. It's one of the limitations we call out in the dataset card.
There are a few though! Try "dog" or "cookie cutter" for example.
Re: We rendered and embedded one million CAD files
#8i tried “apples” and got lots of nuts-and-bolts models? edit: looks like the data is trained from machinery parts. impressive regardless, but i’d add that to the lander
I tried "DHO804" (a popular oscilloscope that has printable accessories), got all screws.
Ok too niche, except that's exactly the use-case as I see it so if that's too niche then what good is it? Whatever call it pre-alpha poc and move on...
Tried "grommet", got all finger rings. Closer but not close enough to be useful. It wasn't a mix of ringular-shaped objects including grommets, and grommets aren't only round either. None of the rings were even slightly grommet shaped, purely tori and belts, some with add-ons and cut-outs.
Perhaps it needs a couple orders of magnitude more input samples before it becomes useful. And by "useful" I do mean even just as a proof of concept, because I don't see any concept proven here.
Re: We rendered and embedded one million CAD files
#9i tried “apples” and got lots of nuts-and-bolts models? edit: looks like the data is trained from machinery parts. impressive regardless, but i’d add that to the lander
I think an apple would not be stored in a CAD format like IGES or STEP but rather in OBJ, USD, FBX etc.
I.e. it would not be in dataset because the use cases for 3D apples are outside of typical use cases where people resort to CAD software.
Re: We rendered and embedded one million CAD files
#10i tried “apples” and got lots of nuts-and-bolts models? edit: looks like the data is trained from machinery parts. impressive regardless, but i’d add that to the lander
There's a pretty big bias for mechanical engineering components in the dataset- very few organic forms. It's one of the limitations we call out in the dataset card. There are a few though! Try "dog" or "cookie cutter" for example.
It's CAD. Is there a legitimate reason to use that to engineer a dog? Doesn't make sense to me.